Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare openWorldHint=true and non-idempotent, but the description adds the operational detail an agent most needs: every call consumes 1 of the site's monthly keyword searches, that quota is shared across all site members, and the response reports the remaining balance. It also names the external provider (DataForSEO) driving variability and explains that zero-volume keywords appear for reference but are not actionable in the calendar — context no annotation conveys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences, front-loaded with purpose and payoff, then quota behavior, then the zero-volume caveat — no filler. The one soft spot is the back-reference 'the same as the Calendar keyword search', which names a UI concept rather than a tool and costs a little parsing effort for an agent without that context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-shape burden and does so thoroughly: field list, result cap (25), provider, and quota consumption reporting. Combined with the calendar-addition limitation, an agent has everything needed to decide whether to call, what it costs, and what comes back.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with only two parameters, and the schema already documents projectId (from list_sites) and the 80-character seedKeyword with an example. The description reinforces the seed concept but contributes no additional syntax, normalization, or constraint detail beyond what the schema states, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Researches keywords for a site') and goes further to enumerate the exact return payload: the seed keyword plus up to 25 related keywords with volume, difficulty, competition, CPC and monthly trend, sourced from DataForSEO. That level of specificity clearly separates it from sibling analytics and insight tools such as get_search_insight or search_analytics_query, and an agent can tell what it gets without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It establishes clear usage context by tying itself to 'the Calendar keyword search' and pointing at get_project for the quota state that governs whether calling is feasible. It also implicitly routes downstream work by noting that zero-volume keywords 'cannot be added to the calendar', which hints at the boundary with add_keywords_to_calendar. What's missing is an explicit statement of when to prefer this over the other search-related siblings (get_search_insight, search_analytics_query), so the agent must infer the alternative from names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.